Merge branch 'main' into DM/schedulers

.clang-format-ignore

@@ -1,26 +1,3 @@
-tests/tt_eager/ops/ccl/test_ccl_reduce_scatter_host_helpers.cpp
-tests/tt_metal/distributed/test_distributed.cpp
-tests/tt_metal/tt_metal/common/device_fixture.hpp
-tests/tt_metal/tt_metal/eth/test_erisc_app_direct_send.cpp
-tests/tt_metal/tt_metal/perf_microbenchmark/routing/kernels/traffic_gen_rx.cpp
-tests/tt_metal/tt_metal/perf_microbenchmark/routing/kernels/traffic_gen_tx.cpp
-tests/tt_metal/tt_metal/perf_microbenchmark/routing/test_bi_tunnel.cpp
-tests/tt_metal/tt_metal/perf_microbenchmark/routing/test_common.hpp
-tests/tt_metal/tt_metal/perf_microbenchmark/routing/test_mux_demux.cpp
-tests/tt_metal/tt_metal/perf_microbenchmark/routing/test_mux_demux_2level.cpp
-tests/tt_metal/tt_metal/perf_microbenchmark/routing/test_tunnel_1cq.cpp
-tests/tt_metal/tt_metal/perf_microbenchmark/routing/test_tunnel_2cq.cpp
-tests/tt_metal/tt_metal/perf_microbenchmark/routing/test_tx_rx.cpp
-tests/tt_metal/tt_metal/perf_microbenchmark/routing/test_uni_tunnel.cpp
-tests/tt_metal/tt_metal/perf_microbenchmark/routing/test_uni_tunnel_single_chip.cpp
-tests/tt_metal/tt_metal/perf_microbenchmark/routing/test_vc_mux_demux.cpp
-tests/tt_metal/tt_metal/perf_microbenchmark/routing/test_vc_uni_tunnel.cpp
-tests/tt_metal/tt_metal/test_compile_sets_kernel_binaries.cpp
-tests/ttnn/unit_tests/gtests/ccl/kernels/fabric_erisc_datamover_sender_worker_sender.cpp
-tests/ttnn/unit_tests/gtests/ccl/kernels/fabric_worker_sender_multi_input.cpp
-tests/ttnn/unit_tests/gtests/ccl/kernels/test_kernels.common.hpp
-tests/ttnn/unit_tests/gtests/ccl/test_fabric_erisc_data_mover_loopback_with_workers.cpp
-tests/ttnn/unit_tests/gtests/test_graph_basic.cpp
 tt_metal/distributed/mesh_device.cpp
 tt_metal/hw/ckernels/blackhole/metal/llk_api/llk_unpack_tilize_api.h
 tt_metal/impl/buffers/buffer.cpp
@@ -54,7 +31,6 @@ tt_metal/llrt/rtoptions.hpp
 tt_metal/llrt/tt_cluster.cpp
 tt_metal/llrt/tt_cluster.hpp
 tt_metal/llrt/tt_memory.h
-tt_metal/tt_metal.cpp
 ttnn/cpp/pybind11/tensor.cpp
 ttnn/cpp/ttnn/device_operation.hpp
 ttnn/cpp/ttnn/graph/graph_processor.cpp
@@ -123,9 +99,33 @@ ttnn/cpp/ttnn/operations/embedding_backward/device/embedding_backward_device_ope
 ttnn/cpp/ttnn/operations/embedding_backward/device/embedding_backward_device_operation.hpp
 ttnn/cpp/ttnn/operations/experimental/ccl/reduce_scatter_async/device/reduce_scatter_async_program.cpp
 ttnn/cpp/ttnn/operations/experimental/matmul/group_attn_matmul/device/kernels/compute/transformer_group_attn_matmul.cpp
-ttnn/cpp/ttnn/operations/pool/maxpool/max_pool2d.cpp
+ttnn/cpp/ttnn/operations/pool/generic/generic_pools.cpp
 ttnn/cpp/ttnn/operations/uniform/device/uniform_device_operation.cpp
 ttnn/cpp/ttnn/operations/uniform/device/uniform_device_operation.hpp
 ttnn/cpp/ttnn/tensor/types.hpp
 
-tests/*
+tests/tt_metal/test_utils/env_vars.hpp
+tests/tt_metal/tt_metal/api/allocator/test_free_list_opt_allocator.cpp
+tests/tt_metal/tt_metal/api/test_global_semaphores.cpp
+tests/tt_metal/tt_metal/dispatch/sub_device_test_utils.hpp
+tests/tt_metal/tt_metal/perf_microbenchmark/10_dram_read_remote_cb_sync/test_dram_read_remote_cb.cpp
+tests/tt_metal/tt_metal/perf_microbenchmark/11_remote_cb_sync_matmul_single_core/test_remote_cb_sync_matmul.cpp
+tests/tt_metal/tt_metal/perf_microbenchmark/routing/kernels/traffic_gen_rx.cpp
+tests/tt_metal/tt_metal/perf_microbenchmark/routing/kernels/traffic_gen_tx.cpp
+tests/tt_metal/tt_metal/perf_microbenchmark/routing/test_common.hpp
+tests/tt_metal/tt_metal/perf_microbenchmark/routing/test_mux_demux.cpp
+tests/tt_metal/tt_metal/perf_microbenchmark/routing/test_mux_demux_2level.cpp
+tests/tt_metal/tt_metal/perf_microbenchmark/routing/test_tx_rx.cpp
+tests/tt_metal/tt_metal/perf_microbenchmark/routing/test_vc_bi_tunnel_2ep.cpp
+tests/tt_metal/tt_metal/perf_microbenchmark/routing/test_vc_bi_tunnel_4ep.cpp
+tests/tt_metal/tt_metal/perf_microbenchmark/routing/test_vc_loopback_tunnel.cpp
+tests/tt_metal/tt_metal/perf_microbenchmark/routing/test_vc_mux_demux.cpp
+tests/tt_metal/tt_metal/perf_microbenchmark/routing/test_vc_uni_tunnel.cpp
+tests/ttnn/unit_tests/gtests/test_ccl_on_galaxy.cpp
+
+# Suspicious Formatting Could Cause Issues
+tests/tt_metal/tt_metal/debug_tools/*
+tests/tt_metal/tt_metal/test_kernels/misc/watcher_asserts.cpp
+tests/tt_metal/tt_metal/test_kernels/misc/watcher_pause.cpp
+tests/tt_metal/tt_metal/test_kernels/misc/watcher_ringbuf.cpp
+tests/tt_metal/tt_metal/test_kernels/misc/watcher_waypoints.cpp

.git-blame-ignore-revs

@@ -1,6 +1,7 @@
 # CMake formatting
 0be480e4450b902174f8c1f03559a8fc6eebb827
-# clang-format-ttnn
+# clang-format
 352e61a97c8d843ac4120aec196e6e062879e98c
-# clang-format-ttmetal
 effbfe00f94b5a46f51f923bee56d6d8044afd01
+1758447481544acd234d1ab7579674bf2429fdd0
+94084b94fbfab32e8d6248255f1dfc166bf80255

.gitattributes

@@ -0,0 +1,2 @@
+
+/cmake/version.cmake export-subst

.github/actions/docker-run/action.yml

@@ -8,7 +8,7 @@ inputs:
   docker_os_arch:
     description: 'Docker image architecture'
     required: false
-    default: ubuntu-20.04-amd64
+    default: tt-metalium/ubuntu-20.04-amd64
   docker_username:
     description: docker login username
     required: true
@@ -89,7 +89,7 @@ runs:
           set -eu
 
           install_wheel=${{ inputs.install_wheel }}
-          if [[ "${install_wheel,,}" == "true" ]]; then
+          if [ "${install_wheel,,}" == "true" ]; then
             WHEEL_FILENAME=$(ls -1 *.whl)
             pip3 install "$WHEEL_FILENAME"
           fi

.github/actions/generate-docker-tag/action.yml

@@ -24,8 +24,8 @@ runs:
     - name: Determine Full Docker Image Tag
       shell: bash
       run: |
-        echo "TT_METAL_DOCKER_IMAGE_TAG=ghcr.io/${{ github.repository }}/tt-metalium/${{ inputs.image }}:${{ env.IMAGE_TAG }}" >> $GITHUB_ENV
-        echo "TT_METAL_REF_IMAGE_TAG=ghcr.io/${{ github.repository }}/tt-metalium/${{ inputs.image }}:latest" >> $GITHUB_ENV
+        echo "TT_METAL_DOCKER_IMAGE_TAG=ghcr.io/${{ github.repository }}/${{ inputs.image }}:${{ env.IMAGE_TAG }}" >> $GITHUB_ENV
+        echo "TT_METAL_REF_IMAGE_TAG=ghcr.io/${{ github.repository }}/${{ inputs.image }}:latest" >> $GITHUB_ENV
     - name: Output Docker Image Tag
       shell: bash
       run: |

.github/pull_request_template.md

@@ -13,4 +13,5 @@ Summarize the changes made and its impact.
 - [ ] Blackhole Post commit (if applicable)
 - [ ] Model regression CI testing passes (if applicable)
 - [ ] Device performance regression CI testing passes (if applicable)
+- [ ] **(For models and ops writers)** Full [new models](https://github.com/tenstorrent/tt-metal/actions/workflows/full-new-models-suite.yaml) tests passes
 - [ ] New/Existing tests provide coverage for changes

.github/workflows/_produce-data.yaml

@@ -22,7 +22,9 @@ on:
       - "(Single-card) Model perf tests"
       - "(Single-card) Device perf tests"
       - "(Single-card) Demo tests"
+      - "(Single-card) Tests for new models"
       - "Nightly fast dispatch tests"
+      - "(Single-card) Tests for new models"
       - "(T3K) T3000 demo tests"
       - "(T3K) T3000 model perf tests"
       - "(T3K) T3000 perplexity tests"
@@ -39,6 +41,7 @@ on:
       - "(TGG) TGG frequent tests"
       - "ttnn - Run sweeps"
       - "Blackhole post-commit tests"
+      - "Custom test dispatch"
     types:
       - completed
 

.github/workflows/all-post-commit-workflows.yaml

@@ -2,6 +2,11 @@ name: "All post-commit tests"
 
 on:
   workflow_call:
+    inputs:
+      build-type:
+        required: false
+        default: Release
+        type: string
   workflow_dispatch:
     inputs:
       build-type:
@@ -73,21 +78,6 @@ jobs:
       build-docker: false
       build-type: ${{ inputs.build-type || 'Release' }}
     secrets: inherit
-  # UMD Unit Tests
-  umd-unit-tests:
-    secrets: inherit
-    strategy:
-      fail-fast: false
-      matrix:
-        test-group: [
-          { arch: grayskull, runner-label: E150 },
-          { arch: wormhole_b0, runner-label: N150 },
-          { arch: wormhole_b0, runner-label: N300 },
-        ]
-    uses: ./.github/workflows/umd-unit-tests.yaml
-    with:
-      arch: ${{ matrix.test-group.arch }}
-      runner-label: ${{ matrix.test-group.runner-label }}
   # Slow Dispatch Unit Tests
   sd-unit-tests:
     needs: build-artifact

.github/workflows/build-artifact.yaml

@@ -99,7 +99,7 @@ jobs:
         id: generate-docker-tag
         uses: ./.github/actions/generate-docker-tag
         with:
-          image: ${{ inputs.os }}
+          image: tt-metalium/${{ inputs.os }}
       - name: Docker login
         uses: docker/login-action@v3
         with:

.github/workflows/build-docker-artifact.yaml

@@ -53,7 +53,7 @@ jobs:
       - name: Determine docker image tag
         uses: ./.github/actions/generate-docker-tag
         with:
-          image: ${{ inputs.os }}
+          image: tt-metalium/${{ inputs.os }}
       - name: Build Docker image and push to GHCR
         if: steps.changed-files-specific.outputs.any_changed == 'true'
         uses: docker/build-push-action@v6

.github/workflows/build.yaml

@@ -50,14 +50,13 @@ jobs:
         with:
           docker_username: ${{ github.actor }}
           docker_password: ${{ secrets.GITHUB_TOKEN }}
-          docker_image_arch: ${{ inputs.arch }}
           docker_opts: |
             -e ARCH_NAME=${{ matrix.arch }}
             --group-add 1457
             -v /home/ubuntu/.ccache-ci:/home/ubuntu/.ccache
             -e CCACHE_DIR=/home/ubuntu/.ccache
             -v /mnt/MLPerf/ccache:/mnt/MLPerf/ccache
-          docker_os_arch: ${{ matrix.build.os }}-amd64
+          docker_os_arch: tt-metalium/${{ matrix.build.os }}-amd64
           run_args: |
             set -eu # basic shell hygiene
             set -x

.github/workflows/code-analysis.yaml

@@ -54,7 +54,7 @@ jobs:
         id: generate-docker-tag
         uses: ./.github/actions/generate-docker-tag
         with:
-          image: ${{ inputs.os }}
+          image: tt-metalium/${{ inputs.os }}
       - name: Docker login
         uses: docker/login-action@v3
         with:

.github/workflows/cpp-ttnn-project.yaml

@@ -27,7 +27,7 @@ jobs:
         id: generate-docker-tag
         uses: ./.github/actions/generate-docker-tag
         with:
-          image: ubuntu-22.04-amd64
+          image: tt-metalium/ubuntu-22.04-amd64
       - name: Docker login
         uses: docker/login-action@v3
         with:

.github/workflows/fast-dispatch-full-regressions-and-models-impl.yaml

@@ -149,8 +149,8 @@ jobs:
       fail-fast: false
       matrix:
         test-config:
-          - model: "wh_b0_unstable"
-            cmd: ./tests/scripts/single_card/nightly/run_wh_b0_unstable.sh
+          - model: "stable_diffusion"
+            cmd: pytest --timeout 900 -n auto tests/nightly/single_card/stable_diffusion
           - model: "mamba 1"
             cmd: pytest --timeout 900 -n auto tests/nightly/single_card/mamba --splits 6 --group 1
           - model: "mamba 2"

.github/workflows/full-new-models-suite.yaml

@@ -0,0 +1,60 @@
+name: "(Single-card) Tests for new models"
+
+on:
+  workflow_dispatch:
+    inputs:
+      build-type:
+        required: false
+        default: Release
+        type: choice
+        options:
+          - Release
+          - Debug
+          - RelWithDebInfo
+          - CI
+
+permissions:
+  actions: read
+  contents: write
+  pull-requests: write
+  pages: write
+  id-token: write
+  packages: write
+
+jobs:
+  build-docker-image-2004:
+    uses: ./.github/workflows/build-docker-artifact.yaml
+    secrets: inherit
+    with:
+      os: ubuntu-20.04-amd64
+  build-artifact:
+    needs: build-docker-image-2004
+    uses: ./.github/workflows/build-artifact.yaml
+    secrets: inherit
+    with:
+      build-docker: false
+      build-type: ${{ inputs.build-type || 'Release' }}
+  build-artifact-profiler:
+    needs: build-docker-image-2004
+    uses: ./.github/workflows/build-artifact.yaml
+    with:
+      tracy: true
+      build-docker: false
+      build-type: ${{ inputs.build-type || 'Release' }}
+    secrets: inherit
+  device-perf-single-card:
+    needs: build-artifact-profiler
+    uses: ./.github/workflows/perf-device-models-impl.yaml
+    secrets: inherit
+  e2e-model-perf-single-card:
+    needs: build-artifact
+    uses: ./.github/workflows/perf-models-impl.yaml
+    secrets: inherit
+  nightly-single-card:
+    needs: build-artifact
+    uses: ./.github/workflows/fast-dispatch-full-regressions-and-models-impl.yaml
+    secrets: inherit
+  demos-single-card:
+    needs: build-artifact
+    uses: ./.github/workflows/single-card-demo-tests-impl.yaml
+    secrets: inherit

.github/workflows/metal-run-microbenchmarks.yaml

@@ -19,6 +19,7 @@ jobs:
           # {arch: wormhole_b0, runs-on: ["pipeline-perf", "N150", "bare-metal", "in-service"]},
           # N300
           {arch: wormhole_b0, runs-on: ["N300", "pipeline-perf", "bare-metal", "in-service"]},
+          {arch: wormhole_b0, runs-on: ["N300", "pipeline-perf", "bare-metal", "in-service"], ccl: true},
         ]
     env:
       TT_METAL_ENV: ${{ vars.TT_METAL_ENV }}
@@ -37,7 +38,14 @@ jobs:
           ./create_venv.sh
       - name: Run microbenchmark tests
         timeout-minutes: 90
-        run: ./tests/scripts/run_tests.sh --tt-arch $ARCH_NAME --pipeline-type microbenchmarks
+        run: |
+          PIPELINE_TYPE="microbenchmarks"
+          if [ "${{ matrix.runner-info.ccl }}" == "true" ]; then
+            PIPELINE_TYPE="ccl_microbenchmarks"
+          else
+            TT_METAL_SLOW_DISPATCH_MODE=1 ./tests/scripts/run_tunneler_tests.sh --machine-type ${{ matrix.runner-info.runs-on[0] }}
+          fi
+          ./tests/scripts/run_tests.sh --tt-arch $ARCH_NAME --pipeline-type "$PIPELINE_TYPE"
       - name: Upload microbenchmark report csvs
         uses: actions/upload-artifact@v4
         with:

.github/workflows/package-and-release.yaml

@@ -180,32 +180,16 @@ jobs:
             infra/machine_setup/scripts/setup_hugepages.py
             metal_libs-*+*.whl
           fail_on_unmatched_files: true
-  create-docker-image:
+  create-docker-release-image:
     needs: [
       create-tag,
       create-and-upload-draft-release
     ]
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-      - name: Login to GitHub Container Registry
-        uses: docker/login-action@v3
-        with:
-          registry: https://ghcr.io
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-      - name: Build and push
-        env:
-          TT_METAL_DOCKER_IMAGE: tt-metalium/ubuntu-20.04-amd64
-        uses: docker/build-push-action@v6
-        with:
-          push: true
-          tags: ghcr.io/${{ github.repository }}/tt-metalium/ubuntu-20.04-amd64:${{ needs.create-tag.outputs.version }}-dev
-          context: .
-          file: dockerfile/ubuntu-20.04-amd64.Dockerfile
+    uses: ./.github/workflows/publish-release-image.yaml
+    secrets: inherit
+    with:
+      version: ${{ needs.create-tag.outputs.version }}
+      is_major_version:  ${{ needs.get-params.outputs.is-release-candidate !='true' && needs.get-params.outputs.should-create-release == 'true' }}
   release-docs:
     needs: [
       get-params,

.github/workflows/publish-release-image-wrapper.yaml

@@ -1,12 +1,28 @@
 name: "Create and Publish Release Docker Image"
 
 on:
-  workflow_call:
   workflow_dispatch:
-
 jobs:
-  to_be_filled_out:
-    steps:
-      - name: This workflow will be filled out in https://github.com/tenstorrent/tt-metal/pull/15013
-        run: |
-          echo "NOOP"
+  build-artifact:
+    uses: ./.github/workflows/build-artifact.yaml
+    secrets: inherit
+  build-wheels:
+    needs: build-artifact
+    strategy:
+      matrix:
+        # Since pre-compiled builds only run on 20.04, we can only test on 20.04 for now
+        # The full 22.04 flow can be tested without precompiled
+        os: [ubuntu-20.04]
+        arch: [grayskull, wormhole_b0]
+    uses: ./.github/workflows/_build-wheels-impl.yaml
+    with:
+      os: ${{ matrix.os }}
+      arch: ${{ matrix.arch }}
+      from-precompiled: true
+  publish-release-image:
+    needs: build-wheels
+    uses: ./.github/workflows/publish-release-image.yaml
+    secrets: inherit
+    with:
+      version: dev-${GITHUB_REF_NAME//\//-}
+      is_major_version: false